Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     enjoying
    0.67
    enjoy
    0.65
     enjoy
    0.59
     belleza
    0.58
    9
    0.56
     beleza
    0.55
     Enjoy
    0.55
    1
    0.55
     entretenimiento
    0.55
     cheveux
    0.55
    POSITIVE LOGITS
     predefined
    0.94
     descriptive
    0.94
     additional
    0.92
     penalties
    0.90
    相应的
    0.89
     techniques
    0.88
     judicious
    0.88
     추가
    0.88
    ――――
    0.87
     explicit
    0.86
    Act Density 3.801%

    No Known Activations